© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12812
    Prev
    Next
    INDEX
    Explanations

    words or phrases describing the monetary value and consumerism of a product, service, or place

    oai_token-act-pair · gemini-2.0-flash

    value for money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bargain
    -0.60
    DoubleQuotes
    -0.57
    RegressionTest
    -0.57
    ArgumentParser
    -0.56
    dö
    -0.54
    utilisons
    -0.53
    bargain
    -0.52
    FunctionFlags
    -0.52
    <bos>
    -0.51
     gjerne
    -0.50
    POSITIVE LOGITS
    invokeLater
    0.60
    TypedDataSet
    0.51
    principalTable
    0.47
    KURZBESCHREIBUNG
    0.46
     Lest
    0.45
    眶
    0.45
    corbic
    0.44
    fäl
    0.44
    ustomed
    0.44
    _{*}
    0.44
    Activations Density 6.546%

    No Known Activations